Proceedings of the NATO Advanced Study Institute on Computational Models of Speech Pattern Processing, held in St. Helier, Jersey, UK, July 7-18, 1997

This book presents a collection of papers from the Spring 1995 Work shop on Computational Approaches to Processing the Prosody of Spon taneous Speech, hosted by the ATR Interpreting Telecommunications Re search Laboratories in Kyoto, Japan. The workshop brought together lead ing researchers in the fields of speech and signal processing, electrical en gineering, psychology, and linguistics, to discuss aspects of spontaneous speech prosody and to suggest approaches to its computational analysis and modelling. The book is divided into four sections. Part I gives an overview and theoretical background to the nature of spontaneous speech, differentiating it from the lab-speech that has been the focus of so many earlier analyses. Part II focuses on the prosodic features of discourse and the structure of the spoken message, Part ilIon the generation and modelling of prosody for computer speech synthesis. Part IV discusses how prosodic information can be used in the context of automatic speech recognition. Each section of the book starts with an invited overview paper to situate the chapters in the context of current research. We feel that this collection of papers offers interesting insights into the scope and nature of the problems concerned with the computational analysis and modelling of real spontaneous speech, and expect that these works will not only form the basis of further developments in each field but also merge to form an integrated computational model of prosody for a better understanding of human processing of the complex interactions of the speech chain.

A new perspective on phonetic variation is achieved in this volume through the construction of a series of models of spoken American English. In the past, computer theorists and programmers investigating pronunciation have often relied on their own knowledge of the language or on limited transcription data. Speech recognition researchers, on the other hand, have drawn on a great deal of data but without examining in detail the information about pronunciation the data contains. The authors combine the best of each approach to develop probabilistic and rule-based computational models of transcription data. An ongoing controversy in studies of phonetic variation is the existence and proper definition of a phonetic unit. The authors argue that assumptions about the units of spoken language are critical to a computational model. Their computational models employ suprasegmental elements such as syllable boundaries, stress, and position in a unit called a metrical foot. The use of such elements in modeling data enables the creation of better computational models for both recognition and synthesis technology. This book should be of interest to speech engineers, linguists, and anyone who wishes to understand symbolic systems of communication.

Human language acquisition has been studied for centuries, but using computational modeling for such studies is a relatively recent trend. However, computational approaches to language learning have become increasingly popular, mainly due to advances in developing machine learning techniques, and the availability of vast collections of experimental data on child language learning and child-adult interaction. Many of the existing computational models attempt to study the complex task of learning a language under cognitive plausibility criteria (such as memory and processing limitations that humans face), and to explain the developmental stages observed in children. By simulating the process of child language learning, computational models can show us which linguistic representations are learnable from the input that children have access to, and which mechanisms yield the same patterns of behaviour that children exhibit during this process. In doing so, computational modeling provides insight into the plausible mechanisms involved in human language acquisition, and inspires the development of better language models and techniques. This book provides an overview of the main research questions in the field of human language acquisition. It reviews the most commonly used computational frameworks, methodologies and resources for modeling child language learning, and the evaluation techniques used for assessing these computational models. The book is aimed at cognitive scientists who want to become familiar with the available computational methods for investigating problems related to human language acquisition, as well as computational linguists who are interested in applying their skills to the study of child language acquisition. Different aspects of language learning are discussed in separate chapters, including the acquisition of the individual words, the general regularities which govern word and sentence form, and the associations between form and meaning. For each of these aspects, the challenges of the task are discussed and the relevant empirical findings on children are summarized. Furthermore, the existing computational models that attempt to simulate the task under study are reviewed, and a number of case studies are presented. Table of Contents: Overview / Computational Models of Language Learning / Learning Words / Putting Words Together / Form--Meaning Associations / Final Thoughts

Speech dynamics refer to the temporal characteristics in all stages of the human speech communication process. This speech “chain” starts with the formation of a linguistic message in a speaker's brain and ends with the arrival of the message in a listener's brain. Given the intricacy of the dynamic speech process and its fundamental importance in human communication, this monograph is intended to provide a comprehensive material on mathematical models of speech dynamics and to address the following issues: How do we make sense of the complex speech process in terms of its functional role of speech communication? How do we quantify the special role of speech timing? How do the dynamics relate to the variability of speech that has often been said to seriously hamper automatic speech recognition? How do we put the dynamic process of speech into a quantitative form to enable detailed analyses? And finally, how can we incorporate the knowledge of speech dynamics into computerized speech analysis and recognition algorithms? The answers to all these questions require building and applying computational models for the dynamic speech process. What are the compelling reasons for carrying out dynamic speech modeling? We provide the answer in two related aspects. First, scientific inquiry into the human speech code has been relentlessly pursued for several decades. As an essential carrier of human intelligence and knowledge, speech is the most natural form of human communication. Embedded in the speech code are linguistic (as well as para-linguistic) messages, which are conveyed through four levels of the speech chain. Underlying the robust encoding and transmission of the linguistic messages are the speech dynamics at all the four levels. Mathematical modeling of speech dynamics provides an effective tool in the scientific methods of studying the speech chain. Such scientific studies help understand why humans speak as they do and how humans exploit redundancy and variability by way of multitiered dynamic processes to enhance the efficiency and effectiveness of human speech communication. Second, advancement of human language technology, especially that in automatic recognition of natural-style human speech is also expected to benefit from comprehensive computational modeling of speech dynamics. The limitations of current speech recognition technology are serious and are well known. A commonly acknowledged and frequently discussed weakness of the statistical model underlying current speech recognition technology is the lack of adequate dynamic modeling schemes to provide correlation structure across the temporal speech observation sequence. Unfortunately, due to a variety of reasons, the majority of current research activities in this area favor only incremental modifications and improvements to the existing HMM-based state-of-the-art. For example, while the dynamic and correlation modeling is known to be an important topic, most of the systems nevertheless employ only an ultra-weak form of speech dynamics; e.g., differential or delta parameters. Strong-form dynamic speech modeling, which is the focus of this monograph, may serve as an ultimate solution to this problem. After the introduction chapter, the main body of this monograph consists of four chapters. They cover various aspects of theory, algorithms, and applications of dynamic speech models, and provide a comprehensive survey of the research work in this area spanning over past 20~years. This monograph is intended as advanced materials of speech and signal processing for graudate-level teaching, for professionals and engineering practioners, as well as for seasoned researchers and engineers specialized in speech processing

This collection of papers and abstracts stems from the third meeting in the series of Sperlonga workshops on Cognitive Models of Speech Processing. It presents current research on the structure and organization of the mental lexicon, and on the processes that access that lexicon. The volume starts with discussion of issues in acquisition and consideration of questions such as, 'What is the relationship between vocabulary growth and the acquisition of syntax?', and, 'How does prosodic information, concerning the melodies and rhythms of the language, influence the processes of lexical and syntactic acquisition?'. From acquisition, the papers move on to consider the manner in which contemporary models of spoken word recognition and production can map onto neural models of the recognition and production processes. The issue of exactly what is recognised, and when, is dealt with next - the empirical findings suggest that the function of something to which a word refers is accessed with a different time-course to the form of that something. This has considerable implications for the nature, and content, of lexical representations. Equally important are the findings from the studies of disordered lexical processing, and two papers in this volume address the implications of these disorders for models of lexical representation and process (borrowing from both empirical data and computational modelling). The final paper explores whether neural networks can successfully model certain lexical phenomena that have elsewhere been assumed to require rule-based processes.